Skills for Real Engineers. Straight from my .agents directory.
00-academic-router
Agent skill fromagentscope-ai/OpenJudge
Use when the user wants help with academic papers or citations but it's unclear which specific workflow fits — reviewing a paper, checking a BibTeX file for fake references, or benchmarking multiple LLMs on reference-recommendation accuracy. Also use when the user mentions paper review, peer review, BibTeX verification, citation checking, reference hallucination, or academic literature accuracy and hasn't specified which of those three tasks they mean. This skill is the entry router for the academic-eval suite: it asks one diagnostic question then routes to the right sub-skill.
How to install 00-academic-router
npx skills add agentscope-ai/OpenJudge# or add only this skill to Claude Code: copy the folder
skills/academic-eval/00-academic-router/
# into
~/.claude/skills/00-academic-router/ (all projects)
.claude/skills/00-academic-router/ (one project)
1# Academic Eval Router23Entry router for the `academic-eval` suite. You diagnose what the user actually4wants and route them to one of three sub-skills. You don't review papers, verify5BibTeX files, or run arena benchmarks yourself — you're the triage desk.67Each sub-skill is self-contained: it carries inline everything it needs, so it can8be installed and used on its own.910## Diagnostic Question1112Ask (unless the user's request already makes the answer obvious):1314```15To route you correctly, which of these matches what you want?1617a) Review a single paper (PDF or LaTeX source) for correctness/quality/novelty18 — optionally also check its bibliography19b) Check a standalone .bib file for fabricated or mismatched references20 (no paper review needed)21c) Benchmark/compare multiple LLMs on how often they hallucinate references22 when asked to recommend citations (arena-style, many queries)23```2425**Shortcut rule**: if the user already said "review my paper", "check this PDF",26"verify this .bib file", or "compare models on reference hallucination", skip the27question — the routing is already clear from their phrasing.2829## Triage Table3031| User says / has | Use workflow | What it does |32|---|---|---|33| "Review this paper" (PDF or `.tar.gz`/`.zip` TeX source) | `01-paper-review` | Multi-stage review: safety, correctness, quality/novelty score, criticality — optionally + BibTeX check |34…
Excerpt shown under the repository's Apache-2.0 license.
More skills in OpenJudge
Similar skill repositories
An agentic skills framework & software development methodology that works.
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
Public repository for Agent Skills
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
